AgentDrive MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTDRIVE_API_KEY | Yes | Your AgentDrive API key (required). | |
| AGENTDRIVE_API_URL | No | Override the API endpoint (optional, default https://app.agentdrive.sh). | |
| AGENTDRIVE_AGENT_ROLE | No | Free-text role label for the agent (optional). | |
| AGENTDRIVE_AGENT_PLATFORM | No | Agent runtime platform identifier (optional, one of claude-code, codex, cursor, langgraph, crewai, autogen, cline, continue, zed, unknown; default claude-code). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| drive_writeB | Write a markdown file to a workspace. Creates or updates the file with automatic versioning. |
| drive_readB | Read a file's content from a workspace. |
| drive_listA | List files in a workspace, optionally filtered by path prefix. |
| drive_shareA | Generate a share link for a workspace or specific file. Optionally email-gate the link so only a specific person can access it. Humans open this link to view, comment, or edit files. |
| drive_commentC | Add a comment to a file. |
| drive_feedbackB | Read human comments on a file. Use this to check if humans have left feedback. |
| drive_activityB | Get recent activity in a workspace (file writes, comments, shares). |
| drive_inviteA | Invite a human to your organization by email. They will receive a verification code to join. |
| drive_rolesA | Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit). |
| drive_orgA | View your organization details: agents, members, plan, and usage. |
| drive_deleteC | Delete a file from a workspace. |
| drive_versionsB | View version history for a file in a workspace. |
| drive_searchA | Semantic search across your org's artifacts in AgentDrive. Returns the top-N most relevant files. Use this BEFORE writing similar artifacts to avoid duplication and surface prior context. |
| drive_recallA | Recall persistent facts and preferences your agents have written. In v1 this returns semantic search results across artifacts; v1.5 will narrow to auto-extracted facts (preferences, decisions, key entities). |
| drive_log_runA | Log an agent run to AgentDrive's provenance store. Captures task, status, referenced/produced artifacts, and cross-platform identity (which agent on which tool). Used for retrospective context retrieval and team-wide audit. |
| drive_contextA | Auto-pull the most relevant artifacts from prior agent sessions for the task you are about to do. Combines semantic relevance with recency. Call this at the START of any non-trivial task to ground the agent in prior context — replaces manual copy-paste of artifacts between sessions. |
| drive_sandbox_cloneA | [EXPERIMENTAL] Clone a git repo into a per-workspace Linux sandbox. Requires Cloudflare Containers on the AgentDrive worker; gracefully degrades to a 503 with "sandbox not configured" otherwise. |
| drive_sandbox_execA | [EXPERIMENTAL] Run a shell command inside the per-workspace Linux sandbox. Captures stdout/stderr (64 KB cap), exit code, duration. Requires Cloudflare Containers; degrades to 503 otherwise. |
| drive_sandbox_readA | [EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise. |
| drive_sandbox_commitA | [EXPERIMENTAL] Stage + commit the current sandbox worktree. Surfaces as an AgentDrive artifact at commits/.json. Requires Cloudflare Containers; degrades to 503 otherwise. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |